Story: I am a computational biologist who wants to get Census integrated embeddings and their models to perform downstream analysis in my platform and toolkit of choice, for example scanpy in Python.
Substory: I would like to read and follow some executable examples to learn how to access the assets that CELLxGENE hosts
Product requirement: Per-tier sites providing detailed information about the tier and the associated projects.
All tiers should provide a description of the tier.
Tiers 2 and Tier 1 should provide links (for ease of viewing) to our own site with an embedded notebooks: tier-wide notebooks and project-specific notebooks.
All tiers should provide per-project information and metadata:
Tier 3 per project info:
Title
Description
Submitter
Submitter affiliation
DOI [optional]
Model link [optional]
Embeddings link [optional]
Any other free-form links.
Tier 2 per project (embedding) info:
Title
Description
ID for loading
Submitter
Submitter affiliation
DOI [optional]
Model link [optional]
Notebooks links [optional]
Census LTS release associated with the contribution (specified as a Census LTS tag)
Experiment name (e.g., "homo_sapiens")
Measurement name (e.g., "RNA")
Contribution type: the type of the data. Currently must be "obs embedding". Future extensions may include "gene embedding", etc.
Tier 1 per project info:
Title
Description
ID for loading
Model parameters and embedding details – this information will be long format 2-3 paragraphs
Story: I am a computational biologist who wants to get Census integrated embeddings and their models to perform downstream analysis in my platform and toolkit of choice, for example scanpy in Python.
Substory: I would like to read and follow some executable examples to learn how to access the assets that CELLxGENE hosts
Product requirement: Per-tier sites providing detailed information about the tier and the associated projects.